{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QLAX4F2VVJE3IBHWISSNQVWMCP","short_pith_number":"pith:QLAX4F2V","schema_version":"1.0","canonical_sha256":"82c17e1755aa49b404f644a4d856cc13c16b9f095b1a75d41960e0f985e67e68","source":{"kind":"arxiv","id":"1901.03363","version":1},"attestation_state":"computed","paper":{"title":"ALFAA: Active Learning Fingerprint Based Anti-Aliasing for Correcting Developer Identity Errors in Version Control Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Audris Mockus, Chris Bogart, Russell Zaretzki, Sadika Amreen, Yuxia Zhang","submitted_at":"2019-01-10T20:04:33Z","abstract_excerpt":"Graphs of developer networks are important for software engineering research and practice. For these graphs to realistically represent the networks, accurate developer identities are imperative. We aim to identify developer identity errors from open source software repositories in VCS, investigate the nature of these errors, design corrective algorithms, and estimate the impact of the errors on networks inferred from this data. We investigate these questions using over 1B Git commits with over 23M recorded author identities. By inspecting the author strings that occur most frequently, we group"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1901.03363","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2019-01-10T20:04:33Z","cross_cats_sorted":[],"title_canon_sha256":"017c696ff64cfaf2c8bed1f63bf9b638ce5de87e07c210d0c3b2b7693c67a5dd","abstract_canon_sha256":"5dcc5211e32982388a6557d26366caf7247a968eb70a3803168bf85978574d0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:31.453527Z","signature_b64":"dZ70z+oUIx1uCzPjTB6p4glGP/P8hgzlk3f/IMcWpGsM0MseIzuAzGdVdP2O0neUxkA8gAAyMPrbhIqCrF8qBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82c17e1755aa49b404f644a4d856cc13c16b9f095b1a75d41960e0f985e67e68","last_reissued_at":"2026-05-17T23:56:31.453113Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:31.453113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALFAA: Active Learning Fingerprint Based Anti-Aliasing for Correcting Developer Identity Errors in Version Control Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Audris Mockus, Chris Bogart, Russell Zaretzki, Sadika Amreen, Yuxia Zhang","submitted_at":"2019-01-10T20:04:33Z","abstract_excerpt":"Graphs of developer networks are important for software engineering research and practice. For these graphs to realistically represent the networks, accurate developer identities are imperative. We aim to identify developer identity errors from open source software repositories in VCS, investigate the nature of these errors, design corrective algorithms, and estimate the impact of the errors on networks inferred from this data. We investigate these questions using over 1B Git commits with over 23M recorded author identities. By inspecting the author strings that occur most frequently, we group"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.03363","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1901.03363","created_at":"2026-05-17T23:56:31.453183+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.03363v1","created_at":"2026-05-17T23:56:31.453183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.03363","created_at":"2026-05-17T23:56:31.453183+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLAX4F2VVJE3","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLAX4F2VVJE3IBHW","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLAX4F2V","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLAX4F2VVJE3IBHWISSNQVWMCP","json":"https://pith.science/pith/QLAX4F2VVJE3IBHWISSNQVWMCP.json","graph_json":"https://pith.science/api/pith-number/QLAX4F2VVJE3IBHWISSNQVWMCP/graph.json","events_json":"https://pith.science/api/pith-number/QLAX4F2VVJE3IBHWISSNQVWMCP/events.json","paper":"https://pith.science/paper/QLAX4F2V"},"agent_actions":{"view_html":"https://pith.science/pith/QLAX4F2VVJE3IBHWISSNQVWMCP","download_json":"https://pith.science/pith/QLAX4F2VVJE3IBHWISSNQVWMCP.json","view_paper":"https://pith.science/paper/QLAX4F2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.03363&json=true","fetch_graph":"https://pith.science/api/pith-number/QLAX4F2VVJE3IBHWISSNQVWMCP/graph.json","fetch_events":"https://pith.science/api/pith-number/QLAX4F2VVJE3IBHWISSNQVWMCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLAX4F2VVJE3IBHWISSNQVWMCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLAX4F2VVJE3IBHWISSNQVWMCP/action/storage_attestation","attest_author":"https://pith.science/pith/QLAX4F2VVJE3IBHWISSNQVWMCP/action/author_attestation","sign_citation":"https://pith.science/pith/QLAX4F2VVJE3IBHWISSNQVWMCP/action/citation_signature","submit_replication":"https://pith.science/pith/QLAX4F2VVJE3IBHWISSNQVWMCP/action/replication_record"}},"created_at":"2026-05-17T23:56:31.453183+00:00","updated_at":"2026-05-17T23:56:31.453183+00:00"}